Related papers: TRA: Better Length Generalisation with Threshold R…
We present a generalization of Transformers to any-order permutation invariant data (sets, graphs, and hypergraphs). We begin by observing that Transformers generalize DeepSets, or first-order (set-input) permutation invariant MLPs. Then,…
Transformer-based models have become ubiquitous in natural language processing thanks to their large capacity, innate parallelism and high performance. The contextualizing component of a Transformer block is the $\textit{pairwise…
Transformers flexibly operate over sets of real-valued vectors representing task-specific entities and their attributes, where each vector might encode one word-piece token and its position in a sequence, or some piece of information that…
Length Generalization is the essential capacity of autonomous agents to perform tasks in longer contexts than those encountered during training. To systematically study this feat, we test how well models can approximate the next token…
While transformer models exhibit strong in-context learning (ICL) abilities, they often fail to generalize under simple distribution shifts. We analyze these failures and identify Softmax, the scoring function in the attention mechanism, as…
In both Computer Vision and the wider Deep Learning field, the Transformer architecture is well-established as state-of-the-art for many applications. For Multitask Learning, however, where there may be many more queries necessary compared…
Attention-based transformer networks have demonstrated promising potential as their applications extend from natural language processing to vision. However, despite the recent improvements, such as sub-quadratic attention approximation and…
Vision Transformers (ViTs) with self-attention modules have recently achieved great empirical success in many vision tasks. Due to non-convex interactions across layers, however, theoretical learning and generalization analysis is mostly…
Attention is a key part of the transformer architecture. It is a sequence-to-sequence mapping that transforms each sequence element into a weighted sum of values. The weights are typically obtained as the softmax of dot products between…
Transformers have demonstrated great success in numerous domains including natural language processing and bioinformatics. This success stems from the use of the attention mechanism by these models in order to represent and propagate…
Transformers are increasingly dominating multi-modal reasoning tasks, such as visual question answering, achieving state-of-the-art results thanks to their ability to contextualize information using the self-attention and co-attention…
Transformers are state-of-the-art in a wide range of NLP tasks and have also been applied to many real-world products. Understanding the reliability and certainty of transformer model predictions is crucial for building trustable machine…
The Transformer architecture model, based on self-attention and multi-head attention, has achieved remarkable success in offline end-to-end Automatic Speech Recognition (ASR). However, self-attention and multi-head attention cannot be…
While the traditional formulation of machine learning tasks is in terms of performance on average, in practice we are often interested in how well a trained model performs on rare or difficult data points at test time. To achieve more…
The pursuit of computational efficiency has driven the adoption of low-precision formats for training transformer models. However, this progress is often hindered by notorious training instabilities. This paper provides the first…
The self-attention mechanism, at the heart of the Transformer model, is able to effectively model pairwise interactions between tokens. However, numerous recent works have shown that it is unable to perform basic tasks involving detecting…
Relational reasoning is a central component of generally intelligent systems, enabling robust and data-efficient inductive generalization. Recent empirical evidence shows that many existing neural architectures, including Transformers,…
Transformers have demonstrated a competitive performance across a wide range of vision tasks, while it is very expensive to compute the global self-attention. Many methods limit the range of attention within a local window to reduce…
Multi-query attention (MQA), which only uses a single key-value head, drastically speeds up decoder inference. However, MQA can lead to quality degradation, and moreover it may not be desirable to train a separate model just for faster…
Transformer models have been widely adopted in various domains over the last years, and especially large language models have advanced the field of AI significantly. Due to their size, the capability of these networks has increased…